目录

• Outline
• Recap
• Neural Network
• Here comes Deep Learning
• Heros
• Fully connected layer
• Multi-Layers

Outline

• Matmul

• Neural Network

• Deep Learning

• Multi-Layer

Recap

• out = f(X@W + b)

• out = relut(X@W + b)

Neural Network

• h = relut(X@W + b)

• h0=relu(X@W1+b1)$h_0=relu(X@W_1+b_1)$ # Input

• h1=relu(h0@W2+b2)$h_1=relu(h_0@W_2+b_2)$ # Hidden

• out=relu(h1@W3+b3)$out=relu(h_1@W_3+b_3)$ # Output

• Neural Network in the 1980s

  • 3~5 layers

Here comes Deep Learning

• Deep Learning now
  • n≈1200layers$n\approx 1200layers$

Heros

推动深度学习发展的功臣：

• BigDATA
• ReLU
• Dropout
• BatchNorm
• ResNet
• Xavier Initialization
• Caffe/TensorFlow/PyTorch
• ...

Fully connected layer

import tensorflow as tf

x = tf.random.normal([4, 784])

net = tf.keras.layers.Dense(512)
out = net(x)

out.shape

TensorShape([4, 512])

net.kernel.shape, net.bias.shape

(TensorShape([784, 512]), TensorShape([512]))

net = tf.keras.layers.Dense(10)
try:
    net.bias
except Exception as e:
    print(e)

'Dense' object has no attribute 'bias'

net.get_weights()

[]

net.weights

[]

net.build(input_shape=(None, 4))
net.kernel.shape, net.bias.shape

(TensorShape([4, 10]), TensorShape([10]))

net.build(input_shape=(None, 20))
net.kernel.shape, net.bias.shape

(TensorShape([20, 10]), TensorShape([10]))

net.build(input_shape=(2, 4))
net.kernel

<tf.Variable 'kernel:0' shape=(4, 10) dtype=float32, numpy=
array([[ 0.39824653, -0.56459695,  0.15540016, -0.25054374, -0.33711377,
        -0.49766102, -0.27644783, -0.4385618 ,  0.6163305 ,  0.40391672],
       [ 0.14267981,  0.04587489, -0.34641156,  0.41443396,  0.5877181 ,
        -0.58475596,  0.6121434 ,  0.3081839 , -0.29890376,  0.54232216],
       [-0.61803645,  0.31125462,  0.40059066, -0.54361427, -0.6469191 ,
         0.39140797, -0.53628796,  0.59679496,  0.41008878, -0.45868778],
       [ 0.07785475, -0.45004582, -0.42372018, -0.39478874,  0.08843976,
         0.09751028,  0.625625  ,  0.2192722 , -0.527462  ,  0.5550728 ]],
      dtype=float32)>

Multi-Layers

• keras.Sequential([layer1,layer2,layer3])

from tensorflow import keras

x = tf.random.normal([2, 3])
model = keras.Sequential([
    keras.layers.Dense(2, activation='relu'),
    keras.layers.Dense(2, activation='relu'),
    keras.layers.Dense(2)
])
model.build(input_shape=[None, 3])

model.summary()
# [w1,b1,w2,b2,w3,b3]

for p in model.trainable_variables:

print(p.name, p.shape)

Model: "sequential3"


Layer (type)                 Output Shape              Param #

=================================================================

dense13 (Dense)             multiple                  8


dense14 (Dense)             multiple                  6


dense_15 (Dense)             multiple                  6

Total params: 20
Trainable params: 20
Non-trainable params: 0
_
dense13/kernel:0 (3, 2)
dense13/bias:0 (2,)
dense14/kernel:0 (2, 2)
dense14/bias:0 (2,)
dense15/kernel:0 (2, 2)
dense15/bias:0 (2,)